In this paper we address the problem of constructing reliable neural-net implementations, given the assumption that any particular implementation will not be totally correct. The approach taken in this paper is to organize the inevitable errors so as to minimize their impact in the context of a multiversion system, i.e., the system functionality is reproduced in multiple versions, which togethe...

This paper investigates two different neural architectures for the task of relation classification: convolutional neural networks and recurrent neural networks. For both models, we demonstrate the effect of different architectural choices. We present a new context representation for convolutional neural networks for relation classification (extended middle context). Furthermore, we propose conn...

‎Linear semi-infinite programming problem is an important class of optimization problems which deals with infinite constraints‎. ‎In this paper‎, ‎to solve this problem‎, ‎we combine a discretization method and a neural network method‎. ‎By a simple discretization of the infinite constraints,we convert the linear semi-infinite programming problem into linear programming problem‎. ‎Then‎, ‎we use...

A recurrent neural network is presented for solving systems of quadratic programming problems with equality constraints involving complex-valued coefficients. The proposed recurrent neural network is asymptotically stable and able to generate optimal solutions to quadratic programs with equality constraints. An opamp based analogue circuit realization of the recurrent neural network is describe...

We develop a sequential learning model using a recurrent neural network architecture and reinforcement learning to recognize and count objects in images. Simple feedforward neural networks perform well on this task when trained using backpropagation; however, convolutional neural networks are computationally expensive and results are less certain when the image input has imperfect resolution ou...

A novel global hybrid algorithm for feedforward neural networks p. 9 Study on relationship between NIHSS and TCM-SSASD based on the BP neural network multiple models method p. 17 Application of back-propagation neural network to power transformer insulation diagnosis p. 26 Momentum BP neural networks in structural damage detection based on static displacements and natural frequencies p. 35 Defo...

This paper presents a novel approach using recurrent neural networks for estimating the quality of machine translation output. A sequence of vectors made by the prediction method is used as the input of the final recurrent neural network. The prediction method uses bi-directional recurrent neural network architecture both on source and target sentence to fully utilize the bi-directional quality...

A recurrent neural network is applied for minimizing the infinity-norm of joint torques in redundant manipulators. The recurrent neural network explicitly minimizes the maximum component of joint torques in magnitude while keeping the relation between the joint torque and the end-effector acceleration satisfied. The end-effector accelerations are given to the recurrent neural network as its inp...